mihirp1998 / AlignProp
AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion
☆281Updated 5 months ago
Alternatives and similar repositories for AlignProp:
Users that are interested in AlignProp are comparing it to the libraries listed below
- Code for "Diffusion Model Alignment Using Direct Preference Optimization"☆461Updated 2 months ago
- [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"☆218Updated last year
- Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024☆338Updated 7 months ago
- Official implementation of "Controlling Text-to-Image Diffusion by Orthogonal Finetuning".☆290Updated 6 months ago
- [NeurIPS 2024] ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization☆135Updated 2 months ago
- GenEval: An object-focused framework for evaluating text-to-image alignment☆246Updated last month
- VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation☆225Updated 3 weeks ago
- [Neurips 2023 & TPAMI] T2I-CompBench (++) for Compositional Text-to-image Generation Evaluation☆250Updated 2 weeks ago
- (CVPR 2024) 🧩 TokenCompose: Text-to-Image Diffusion with Token-level Supervision☆122Updated 4 months ago
- [NeurIPS 2024] CV-VAE: A Compatible Video VAE for Latent Generative Video Models☆274Updated 4 months ago
- [WACV 2024] Training-Free Layout Control with Cross-Attention Guidance☆257Updated last year
- [ICCV 2023] Efficient Diffusion Training via Min-SNR Weighting Strategy☆245Updated 4 months ago
- 🔥 [CVPR2024] Official implementation of "Self-correcting LLM-controlled Diffusion Models (SLD)☆172Updated last year
- [CVPR 2025] Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization☆205Updated 2 weeks ago
- Better Aligning Text-to-Image Models with Human Preference. ICCV 2023☆282Updated last year
- MoVQGAN - model for the image encoding and reconstruction☆233Updated last year
- Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope…☆270Updated last month
- Official pytorch implementation of the paper: "An Edit Friendly DDPM Noise Space: Inversion and Manipulations". CVPR 2024.☆332Updated 9 months ago
- [ICLR 2025] OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation☆284Updated last month
- 🚀 Cross attention map tools for huggingface/diffusers☆262Updated 3 months ago
- An implementation of the Prompt-to-Prompt paper for the SDXL architecture☆108Updated 10 months ago
- [CVPR2025] PyTorch-based reimplementation of CrossFlow, as proposed in 'Flowing from Words to Pixels: A Noise-Free Framework for Cross-Mo…☆164Updated last month
- ☆122Updated 9 months ago
- Implementation of "DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning"☆91Updated last year
- A one-stop library to standardize the inference and evaluation of all the conditional image generation models. (ICLR 2024)☆167Updated last week
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis☆485Updated 11 months ago
- [ICLR 2025] Rectified Diffusion: Straightness Is Not Your Need☆215Updated last month
- [CVPR 2024] Official implementation of CVPR 2024 paper: "Inversion-Free Image Editing with Natural Language"☆328Updated 10 months ago
- STAR: Scale-wise Text-to-image generation via Auto-Regressive representations☆140Updated 2 months ago
- [NeurIPS 2023 Spotlight] Real-World Image Variation by Aligning Diffusion Inversion Chain☆149Updated last year